Training in progress, step 3180

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:449b0456ed907278d717bbe2c49471a5b377c4798157d35a432eff30e347e295
+oid sha256:b7994599810a8561b1a36ac4fe4c9e95f4dce541d3db2954091dd3d2a8ccb084
 size 268290900

run-9/checkpoint-3180/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96ca691df0adddeb83e16d4304141836de31a703dd6c24e13ded05debd1445fb
+oid sha256:b7994599810a8561b1a36ac4fe4c9e95f4dce541d3db2954091dd3d2a8ccb084
 size 268290900

run-9/checkpoint-3180/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfab5955401e14a359af5a2a1ad8c4baa2163754ef1dd3b2d507e9900167503
+oid sha256:7ecc9a3b4e6c98eaa15419691058d30b921a04b672f5352c23fad3fa71432107
 size 536643898

run-9/checkpoint-3180/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

run-9/checkpoint-3180/trainer_state.json

@@ -10,153 +10,153 @@
   "log_history": [
     {
       "epoch": 0.9968553459119497,
-      "grad_norm": 0.6426376700401306,
+      "grad_norm": 0.6535611152648926,
       "learning_rate": 1.8006289308176103e-05,
-      "loss": 0.4066,
+      "loss": 0.4233,
       "step": 317
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5858064516129032,
-      "eval_loss": 0.20339493453502655,
-      "eval_runtime": 1.4321,
-      "eval_samples_per_second": 2164.591,
-      "eval_steps_per_second": 45.387,
+      "eval_accuracy": 0.5961290322580645,
+      "eval_loss": 0.21176914870738983,
+      "eval_runtime": 1.4165,
+      "eval_samples_per_second": 2188.469,
+      "eval_steps_per_second": 45.887,
       "step": 318
     },
     {
       "epoch": 1.9937106918238994,
-      "grad_norm": 0.5432497262954712,
+      "grad_norm": 0.5437920689582825,
       "learning_rate": 1.6012578616352204e-05,
-      "loss": 0.1687,
+      "loss": 0.1748,
       "step": 634
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.834516129032258,
-      "eval_loss": 0.0972379595041275,
-      "eval_runtime": 1.4451,
-      "eval_samples_per_second": 2145.225,
-      "eval_steps_per_second": 44.981,
+      "eval_accuracy": 0.8367741935483871,
+      "eval_loss": 0.09956149011850357,
+      "eval_runtime": 1.4209,
+      "eval_samples_per_second": 2181.69,
+      "eval_steps_per_second": 45.745,
       "step": 636
     },
     {
       "epoch": 2.990566037735849,
-      "grad_norm": 0.44530677795410156,
+      "grad_norm": 0.45098331570625305,
       "learning_rate": 1.4018867924528304e-05,
-      "loss": 0.1039,
+      "loss": 0.1063,
       "step": 951
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8809677419354839,
-      "eval_loss": 0.063512422144413,
-      "eval_runtime": 1.8258,
-      "eval_samples_per_second": 1697.885,
-      "eval_steps_per_second": 35.601,
+      "eval_accuracy": 0.8832258064516129,
+      "eval_loss": 0.06408421695232391,
+      "eval_runtime": 1.5582,
+      "eval_samples_per_second": 1989.518,
+      "eval_steps_per_second": 41.716,
       "step": 954
     },
     {
       "epoch": 3.9874213836477987,
-      "grad_norm": 0.3926273286342621,
+      "grad_norm": 0.39896130561828613,
       "learning_rate": 1.2025157232704403e-05,
-      "loss": 0.0771,
+      "loss": 0.0783,
       "step": 1268
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.902258064516129,
-      "eval_loss": 0.0473199263215065,
-      "eval_runtime": 1.4505,
-      "eval_samples_per_second": 2137.145,
-      "eval_steps_per_second": 44.811,
+      "eval_accuracy": 0.9029032258064517,
+      "eval_loss": 0.04733781889081001,
+      "eval_runtime": 1.607,
+      "eval_samples_per_second": 1929.024,
+      "eval_steps_per_second": 40.447,
       "step": 1272
     },
     {
       "epoch": 4.984276729559748,
-      "grad_norm": 0.29275721311569214,
+      "grad_norm": 0.30205774307250977,
       "learning_rate": 1.0031446540880504e-05,
-      "loss": 0.0627,
+      "loss": 0.0634,
       "step": 1585
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9116129032258065,
-      "eval_loss": 0.03906334564089775,
-      "eval_runtime": 1.6337,
-      "eval_samples_per_second": 1897.578,
-      "eval_steps_per_second": 39.788,
+      "eval_accuracy": 0.9138709677419354,
+      "eval_loss": 0.03890981525182724,
+      "eval_runtime": 1.7915,
+      "eval_samples_per_second": 1730.43,
+      "eval_steps_per_second": 36.283,
       "step": 1590
     },
     {
       "epoch": 5.981132075471698,
-      "grad_norm": 0.3657830059528351,
+      "grad_norm": 0.3705131709575653,
       "learning_rate": 8.037735849056606e-06,
-      "loss": 0.0543,
+      "loss": 0.0548,
       "step": 1902
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9161290322580645,
-      "eval_loss": 0.033730994910001755,
-      "eval_runtime": 1.6414,
-      "eval_samples_per_second": 1888.576,
-      "eval_steps_per_second": 39.599,
+      "eval_accuracy": 0.9187096774193548,
+      "eval_loss": 0.033547185361385345,
+      "eval_runtime": 1.4256,
+      "eval_samples_per_second": 2174.523,
+      "eval_steps_per_second": 45.595,
       "step": 1908
     },
     {
       "epoch": 6.977987421383648,
-      "grad_norm": 0.24240043759346008,
+      "grad_norm": 0.24667233228683472,
       "learning_rate": 6.044025157232704e-06,
-      "loss": 0.0492,
+      "loss": 0.0495,
       "step": 2219
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.9248387096774193,
-      "eval_loss": 0.03098563477396965,
-      "eval_runtime": 1.4557,
-      "eval_samples_per_second": 2129.568,
-      "eval_steps_per_second": 44.652,
+      "eval_accuracy": 0.9258064516129032,
+      "eval_loss": 0.030793186277151108,
+      "eval_runtime": 1.4222,
+      "eval_samples_per_second": 2179.706,
+      "eval_steps_per_second": 45.704,
       "step": 2226
     },
     {
       "epoch": 7.9748427672955975,
-      "grad_norm": 0.2646857798099518,
+      "grad_norm": 0.2718242406845093,
       "learning_rate": 4.0503144654088055e-06,
-      "loss": 0.0459,
+      "loss": 0.0462,
       "step": 2536
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9264516129032258,
-      "eval_loss": 0.028846168890595436,
-      "eval_runtime": 1.4498,
-      "eval_samples_per_second": 2138.213,
-      "eval_steps_per_second": 44.833,
+      "eval_accuracy": 0.9274193548387096,
+      "eval_loss": 0.028662633150815964,
+      "eval_runtime": 1.6,
+      "eval_samples_per_second": 1937.522,
+      "eval_steps_per_second": 40.625,
       "step": 2544
     },
     {
       "epoch": 8.971698113207546,
-      "grad_norm": 0.2623918354511261,
+      "grad_norm": 0.2668038308620453,
       "learning_rate": 2.056603773584906e-06,
-      "loss": 0.0436,
+      "loss": 0.0439,
       "step": 2853
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.9283870967741935,
-      "eval_loss": 0.02780742570757866,
-      "eval_runtime": 1.4529,
-      "eval_samples_per_second": 2133.625,
-      "eval_steps_per_second": 44.737,
+      "eval_accuracy": 0.9293548387096774,
+      "eval_loss": 0.027632692828774452,
+      "eval_runtime": 1.7922,
+      "eval_samples_per_second": 1729.756,
+      "eval_steps_per_second": 36.269,
       "step": 2862
     },
     {
       "epoch": 9.968553459119496,
-      "grad_norm": 0.2080601304769516,
+      "grad_norm": 0.21342052519321442,
       "learning_rate": 6.289308176100629e-08,
-      "loss": 0.0425,
+      "loss": 0.0428,
       "step": 3170
     }
   ],
@@ -181,8 +181,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9032578479091515,
+    "alpha": 0.7220003069597626,
     "num_train_epochs": 10,
-    "temperature": 9
+    "temperature": 7
   }
 }

run-9/checkpoint-3180/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3137b02b8923ebf435934590b49ed56aba6be0c7863070fc4fceaac8c528c97
+oid sha256:1b98f0ca62fb4c924aefdc18594db45dd3412cdcbb1ffeb21f316d6966c1725b
 size 5368

runs/Dec21_12-52-13_P920/events.out.tfevents.1734760857.P920.912596.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55c5e6ee0d0de5e82b3afb665ca79ab923554186e268d6f4fc067f1eb21904d
+size 15248

runs/Dec21_12-52-13_P920/events.out.tfevents.1734760936.P920.912596.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccae6a27c1b5f39f6420cf0735b7ad7a40449bc04c509e7d59843af18dfd23b
+size 13112

runs/Dec21_12-52-13_P920/events.out.tfevents.1734760952.P920.912596.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6422ca5ca7fe6374abe62d08e8b4d8b0dfc1ed37b3e013676a914f39383cc194
+size 13112

runs/Dec21_12-52-13_P920/events.out.tfevents.1734760968.P920.912596.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630712a527a4c214c55538c12b47967b7d786ab22ae88638ee265acd9850f256
+size 13112

runs/Dec21_12-52-13_P920/events.out.tfevents.1734760985.P920.912596.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5925228eeab263b4ec9befdba262b30e46d8232b8464ccb90e100b364bc568
+size 18273

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338d7910d3e81567e5c70da214bf92dcb88dbb60030c2a7136a625e1ef38fcfa
+oid sha256:1b98f0ca62fb4c924aefdc18594db45dd3412cdcbb1ffeb21f316d6966c1725b
 size 5368